Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oire
    0.42
    Ｙ
    0.41
    druck
    0.40
    ঙ্গি
    0.39
    𝓎
    0.38
    締め
    0.38
    insel
    0.38
    cherche
    0.37
     साझेदारी
    0.37
    odar
    0.37
    POSITIVE LOGITS
     Tink
    0.44
     Proficiency
    0.43
    Creation
    0.43
    ഞ
    0.42
     figura
    0.41
     Trades
    0.40
    Lear
    0.40
     Verona
    0.40
     boca
    0.39
     Confirmation
    0.39
    Act Density 0.001%

    No Known Activations